GoModel history
Aug 2026 → Nov 2026
openai → openai cell. The engine changed between these runs (f3adbb1 → d240bad), so differences can include instrument changes, not only gateway changes. Changes within ±5% show as roughly unchanged (—); this is a display tolerance, not a statistical margin.
| Reading | Aug 2026 | Nov 2026 | Change | Rank Aug 2026 → Nov 2026 |
|---|---|---|---|---|
| Added latency p50 (µs) | 686 µs | 343 µs | ↑ -50.0% | 9 of 14 → 8 of 15 |
| Added latency p99 (µs) | 2,309 µs | 565 µs | ↑ -75.5% | 9 of 14 → 8 of 15 |
| Throughput, p99 ≤ 1 ms (req/s) | n/a | 4,555 req/s | · | — → 1 of 2 |
| Throughput, p99 ≤ 5 ms (req/s) | 1,671 req/s | 6,685 req/s | ↑ +300.1% | 1 of 2 → 2 of 3 |
| Throughput, p99 ≤ 10 ms (req/s) | 1,738 req/s | 6,862 req/s | ↑ +294.8% | 1 of 1 → 2 of 2 |
| Throughput, p99 unbounded (req/s) | 2,468 req/s | 7,475 req/s | ↑ +202.9% | 5 of 5 → 4 of 4 |
| CPU per request (µs) | 1,172.1 | 439.2 | ↑ -62.5% | 10 of 14 → 8 of 14 |
| Idle RSS (MiB) | 50.8 MiB | 53 MiB | — +4.3% | — → — |
| Peak RSS (MiB) | 86.13 MiB | 90.51 MiB | ↓ +5.1% | — → — |
Runs
2 published runs · Added latency p99 (µs), openai → openai · values describe the recorded local-mock configuration; a missing reading is never zero. Hover a trend for its comparability details.
| Measured | Build | Engine | Result | Trend | Field placement | Evidence |
|---|---|---|---|---|---|---|
| enterpilot/gomodel:0.2.3 | d240bad | 565 µs | Engine changed | 8 of 15 Current field | Run evidence | |
| enterpilot/gomodel:0.1.82 | f3adbb1 | 2,309 µs | First run | 9 of 14 Aug 2026 field | Run evidence |